© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 0-GEMMASCOPE-RES-16K
    6. 7480
    Prev
    Next
    INDEX
    Explanations

    terms related to electric or electrical concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     indeed
    -0.39
     independent
    -0.39
    or
    -0.39
     حوزه
    -0.39
     specialized
    -0.38
     Lauf
    -0.37
     dedicated
    -0.36
     identified
    -0.36
    ↵↵
    -0.36
    IA
    -0.34
    POSITIVE LOGITS
    sizeCache
    0.91
     queſta
    0.84
    ſhip
    0.83
     contextLoads
    0.82
    <unused51>
    0.82
    <unused8>
    0.82
    <unused79>
    0.81
    <unused17>
    0.81
    <unused16>
    0.81
    [@BOS@]
    0.81
    Activations Density 0.235%

    No Known Activations